By Mike Glaser, Cox Communications; Chris Rhinehart, Cox Communications; Ruben Ruiz, Cox Communications; Les Flippen, Cox Communications
Great strides have been made in improving critical facilities availability, reliability, and resiliency.
Additionally, myriad ways have been established to increase sustainability through the use of welldocumented energy conservation measures (ECMs). Over one-third of the energy a multiple-system operator (MSO) consumes is in its critical facilities and data centers, so reduction of energy consumption and the associated reduction in carbon footprint in these spaces contributes to positive movement of the dial on company environmental goals.
After ECMs such as airflow optimization (AFO) and hot aisle/cold aisle configurations are in place, the next level is optimal sensor placement and development of building management systems (BMS) automation and controls algorithms. As the number of data points and disparate sources increases, it becomes clear that artificial intelligence (AI) and machine learning (ML) will be required to optimize and maintain the highest level of operational efficiency through all of the lessons learned, and the constantly changing environment both inside and out of critical facilities.
In this paper there is an overview of ECMs, their impact and lessons learned through deployment, and exploration of possible ways in which AI and ML can be used with BMS controls to optimize efficiency while maintaining expected availability, reliability, and resiliency of critical facilities.